Entire sig-jump-diffusions, their expected signature and applications to score-based generative modeling
math.PR, stat.ML
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/fprimavera/expected_signature_
Terminology
Sources
- Stochastic control with signatures via Riccati equations on the tensor algebra
- Signature approach for pricing and hedging path-dependent options with frictions
- Exponentially Fading Memory Signature
- Expected signature of Gaussian processes with strictly regular kernels
- Diffusion Models for Adaptive Sequential Data Generation
- Lecture notes on rough paths and applications to machine learning
- Schr\"odinger bridges with jumps for time series generation
- Novelty detection on path space
- Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter
- Signature Methods for Optimal Market Making
- Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach
- Learning from the past, predicting the statistics for the future, learning an evolving system
- Path-Dependent SDEs: Solutions and Parameter Estimation
Related papers
- Rank-One HCIZ Integrals and Multiplicative Convolutions
- Repeated averaging on random d-regular graphs
- Precise cover times for branching random walks on Hamming graphs: (iterated) logarithmic corrections
- Markov Chain CLTs: Resolving Open Problems
- Marked stable L'evy processes in Brownian local time
- A Sharp Refinement of Samuels' Inequality via Cap Moves